© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34570
    Prev
    Next
    INDEX
    Explanations

    system namespaces and types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     our
    -1.20
    Bearbeiten
    -1.20
    Aktual
    -1.17
     encantado
    -1.14
    Sempre
    -1.13
     enamorado
    -1.13
     насеља
    -1.11
     یا
    -1.09
     confirmado
    -1.09
     their
    -1.09
    POSITIVE LOGITS
    ge
    1.26
    res
    1.23
    pre
    1.20
    all
    1.15
    are
    1.13
    view
    1.09
    have
    1.09
    T
    1.08
    dis
    1.06
     But
    1.05
    Activations Density 0.019%

    No Known Activations